arXiv 2410.203142024-10-27cs.CVeess.IV

基于小波的Mamba与傅里叶调节用于低光照图像增强

Wavelet-based Mamba with Fourier Adjustment for Low-light Image Enhancement

School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology（上海理工大学光电信息与计算机工程学院）；School of computer science and artificial intelligence, Liaoning Normal University（辽宁师范大学计算机与人工智能学院）；College of computer science and technology, Jilin University（吉林大学计算机科学与技术学院）；School of Computer, National University of Dense Technology（国防科技大学计算机学院）

Junhao Tan, Songwen Pei, Wei Qin, Bo Fu, Ximing Li, Libo Huang

备注：: 18 pages, 8 figures, ACCV2024

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出WalMaFa模型，结合小波域通道级Mamba增强全局亮度与傅里叶调节块细化局部纹理，在低光照图像增强上以更低计算量和更快速度达到SOTA。

摘要：

频率信息（例如离散小波变换和快速傅里叶变换）已被广泛应用于解决低光照图像增强（LLIE）问题。然而，现有的基于频率的模型主要在简单的小波或傅里叶图像空间中运行，未能充分利用每个空间中有效的全局和局部信息。我们发现，小波频率信息由于其低频分量而对全局亮度更敏感，而傅里叶频率信息由于其相位分量而对局部细节更敏感。为了通过将空间通道信息与小波变换中的低频分量进行最优融合来实现更优的初步亮度增强，我们引入了通道级Mamba，它弥补了CNN的长距离依赖，并且与Diffusion和Transformer模型相比具有更低的复杂度。因此，在本工作中，我们提出了一种新颖的基于小波的Mamba与傅里叶调节模型，称为WalMaFa，由基于小波的Mamba块（WMB）和快速傅里叶调节块（FFAB）组成。我们采用编码器-潜空间-解码器结构来完成端到端转换。具体而言，WMB用于编码器和解码器以增强全局亮度，而FFAB用于潜空间以微调局部纹理细节并缓解模糊。大量实验表明，我们提出的WalMaFa以更少的计算资源和更快的速度实现了最先进的性能。代码现已发布于：https://github.com/mcpaulgeorge/WalMaFa。

英文摘要：

Frequency information (e.g., Discrete Wavelet Transform and Fast Fourier Transform) has been widely applied to solve the issue of Low-Light Image Enhancement (LLIE). However, existing frequency-based models primarily operate in the simple wavelet or Fourier space of images, which lacks utilization of valid global and local information in each space. We found that wavelet frequency information is more sensitive to global brightness due to its low-frequency component while Fourier frequency information is more sensitive to local details due to its phase component. In order to achieve superior preliminary brightness enhancement by optimally integrating spatial channel information with low-frequency components in the wavelet transform, we introduce channel-wise Mamba, which compensates for the long-range dependencies of CNNs and has lower complexity compared to Diffusion and Transformer models. So in this work, we propose a novel Wavelet-based Mamba with Fourier Adjustment model called WalMaFa, consisting of a Wavelet-based Mamba Block (WMB) and a Fast Fourier Adjustment Block (FFAB). We employ an Encoder-Latent-Decoder structure to accomplish the end-to-end transformation. Specifically, WMB is adopted in the Encoder and Decoder to enhance global brightness while FFAB is adopted in the Latent to fine-tune local texture details and alleviate ambiguity. Extensive experiments demonstrate that our proposed WalMaFa achieves state-of-the-art performance with fewer computational resources and faster speed. Code is now available at: https://github.com/mcpaulgeorge/WalMaFa.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。